© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 36-GEMMASCOPE-RES-16K
    11. 8193
    Prev
    Next
    INDEX
    Explanations

    concepts related to morality, ethics, and the intersection of faith and society

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 36-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_36/width_16k/average_l0_120
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.36.hook_resid_post
    Hook Layer
    36
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    sweise
    -0.46
    참고
    -0.45
    setVerticalGroup
    -0.44
    的是
    -0.43
    mitglieder
    -0.43
     kaarangay
    -0.41
    чик
    -0.41
    sbereich
    -0.41
    们
    -0.41
    isesi
    -0.40
    POSITIVE LOGITS
     itself
    0.89
    itself
    0.66
     galore
    0.63
     alone
    0.63
    本身
    0.59
     Itself
    0.56
     itſelf
    0.55
    AnimationsModule
    0.52
     samot
    0.51
     above
    0.49
    Activations Density 1.398%

    No Known Activations